FinalProject_JohnBauer

Setup:

Library

NEON MAGs

NEON_metagenomes <- read_tsv("data/NEON/exported_img_data_Gs0161344_NEON.tsv") %>% 
  select(-c(`Domain`, `Sequencing Status`, `Sequencing Center`)) %>% 
  rename(`Genome Name` = `Genome Name / Sample Name`) %>% 
  filter(str_detect(`Genome Name`, 're-annotation', negate = T)) %>% 
  filter(str_detect(`Genome Name`, 'WREF plot', negate = T)) 

NEON_metagenomes <- NEON_metagenomes %>% 
  # Get rid of the the common string "Soil microbial communities from "
  mutate_at("Genome Name", str_replace, "Terrestrial soil microbial communities from ", "") %>% 
  # Use the first `-` to split the column in two
  separate(`Genome Name`, c("Site","Sample Name"), " - ") %>% 
  # Get rid of the the common string "-comp-1"
  mutate_at("Sample Name", str_replace, "-comp-1", "") %>%
  # separate the Sample Name into Site ID and plot info
  separate(`Sample Name`, c("Site ID","subplot.layer.date"), "_", remove = FALSE,) %>% 
  # separate the plot info into 3 columns
  separate(`subplot.layer.date`, c("Subplot", "Layer", "Date"), "-")

NEON_chemistry <- read_tsv("data/NEON/neon_plot_soilChem1_metadata.tsv") %>% 
  # remove -COMP from genomicsSampleID
  mutate_at("genomicsSampleID", str_replace, "-COMP", "") 

NEON_MAGs_metagenomes_chemistry <- NEON_MAGs %>% 
  left_join(NEON_metagenomes, by = "Sample Name") %>% 
  left_join(NEON_chemistry, by = c("Sample Name" = "genomicsSampleID")) %>%
  rename("label" = "Bin ID")

tree_arc <- read.tree("data/NEON/gtdbtk.ar53.decorated.tree")
tree_bac <- read.tree("data/NEON/gtdbtk.bac120.decorated.tree")

#Gammaproteobacteria
NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria <- NEON_MAGs_metagenomes_chemistry %>%
  filter(str_detect(`Class`,"Gammaproteobacteria"))

#Steroidobacterales
NEON_MAGs_metagenomes_chemistry_Steroidobacterales<- NEON_MAGs_metagenomes_chemistry %>%
  filter(str_detect(`Order`,"Steroidobacterales"))
#Burkholderiales
NEON_MAGs_metagenomes_chemistry_Burkholderiales <- NEON_MAGs_metagenomes_chemistry %>%
  filter(str_detect(`Order`,"Burkholderiales"))
#Novel
NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria_Novel <- NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria %>%
  filter(is.na(Order) | is.na(Family) | is.na(Genus) | is.na(Species))
#almost are novel only two have species names



#Toolik
NEON_MAGs_metagenomes_chemistry_TOOL<- NEON_MAGs_metagenomes_chemistry %>% 
  filter(`Site ID.x` == "TOOL") %>%
  mutate(`Genome Size (Kbp)`=as.integer(`Total Number of Bases`/1000))
NEON_MAGs_metagenomes_chemistry_TOOL_Novel <- NEON_MAGs_metagenomes_chemistry_TOOL %>%
  filter(is.na(Order) | is.na(Family) | is.na(Genus) | is.na(Species))
#almost are novel only two have species names
TOOL_MAGs_label <- NEON_MAGs_metagenomes_chemistry_TOOL$label
tree_bac_TOOL_MAGs <-drop.tip(tree_bac,tree_bac$tip.label[-match(TOOL_MAGs_label, tree_bac$tip.label)])

# Make a vector with the internal node lables
node_vector_bac_TOOL_MAGS = c(tree_bac_TOOL_MAGs$tip.label,tree_bac_TOOL_MAGs$node.label)

NEON_MAGs_metagenomes_chemistry_Gamma_noblank <- NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria %>% 
  rename("Orders" = "Order") %>% 
  rename("Phyla" = "Phylum") %>% 
  rename("AssemblyType" = "Assembly Type") %>% 
  rename("WaterpH" ="soilInWaterpH") %>% 
  rename("Temp" ="soilTemp") %>% 
  rename("BinCompleteness" = "Bin Completeness") %>% 
  rename("BinContamination" = "Bin Contamination") %>% 
  rename("TotalNumberofBases" = "Total Number of Bases") %>% 
  rename("EcosystemSubtype" = "Ecosystem Subtype") %>%
  rename("GeneCount" = "Gene Count") %>% 
  rename("GCassembled" = "GC  * assembled")



NEON_MAGs_metagenomes_chemistry_TOOL_noblank <- NEON_MAGs_metagenomes_chemistry_TOOL %>% 
  rename("Phyla" = "Phylum") %>% 
  rename("AssemblyType" = "Assembly Type") %>% 
  rename("WaterpH" ="soilInWaterpH") %>% 
  rename("Temp" ="soilTemp") %>% 
  rename("BinCompleteness" = "Bin Completeness") %>% 
  rename("BinContamination" = "Bin Contamination") %>% 
  rename("TotalNumberofBases" = "Total Number of Bases") %>% 
  rename("EcosystemSubtype" = "Ecosystem Subtype") %>%
  rename("GeneCount" = "Gene Count") %>% 
  rename("GCassembled" = "GC  * assembled")

NEON_MAGs_bact_ind <- NEON_MAGs %>% 
  filter(Domain=="Bacteria") %>% 
  filter(`Assembly Type`=="Individual")
NEON_MAGs_bact_ind_Novel <- NEON_MAGs_bact_ind %>% 
  filter(is.na(Class) | is.na(Order) | is.na(Family) | is.na(Genus) )

NEON_MAGs_metagenomes_chemistry_TOOL_Xanthomonadales <- NEON_MAGs_metagenomes_chemistry_TOOL %>%
  filter(str_detect(`Order`,"Xanthomonadales"))
NEON_MAGs_metagenomes_chemistry_TOOL_Burkholderiales <- NEON_MAGs_metagenomes_chemistry_TOOL %>%
  filter(str_detect(`Order`,"Burkholderiales"))
NEON_MAGs_metagenomes_chemistry_TOOL_Steroidobacterales <- NEON_MAGs_metagenomes_chemistry_TOOL %>%
  filter(str_detect(`Order`,"Steroidobacterales"))

NEON_MAGs_metagenomes_chemistry_Alaska <-NEON_MAGs_metagenomes_chemistry %>%
  filter(str_detect(Site.x,"Alaska"))

Tree Nodes

# Make a vector with the internal node labels
node_vector_bac = c(tree_bac$tip.label,tree_bac$node.label)

# Search for your Phylum, dont sort differently it will mess up nodes
#NEON
phylumss <-NEON_MAGs_metagenomes_chemistry %>%
            count(Phylum, sort=TRUE)
n=1
while (n!=29) {
  if (length(grep(phylumss[n,1], node_vector_bac, value = TRUE))==2) {
       phylumss[n,3] <-match(grep(phylumss[n,1], node_vector_bac, value = TRUE), node_vector_bac)[2]
       }
else {
  phylumss[n,3] <-match(grep(phylumss[n,1], node_vector_bac, value = TRUE), node_vector_bac)[1]
}
  n=n+1
} 
# for some reason they didnt name phylum subpopulations the same way for each, so we have to correct for Desulfobacterota
# grep("Desulfobacterota", node_vector_bac, value = TRUE)
# match(grep("Desulfobacterota", node_vector_bac, value = TRUE), node_vector_bac)
# match(grep("Desulfobacterota_B", node_vector_bac, value = TRUE), node_vector_bac)
phylumss[16,3] <- match(grep(phylumss[16,1], node_vector_bac, value = TRUE), node_vector_bac)[1]

phylumss <-phylumss %>%
    arrange(desc(`...3`))
colortest <-viridis(29)
n=1
while (n!=29) {
  phylumss[n,4] <- colortest[n]
  n=n+1
} 

#Gamma
tree_bac_node_Gammaproteobacteria <- Preorder(tree_bac)
tree_Gammaproteobacteria <- Subtree(tree_bac_node_Gammaproteobacteria, 3048)

# grep("Thermoproteota", node_vector_bac, value = TRUE)
# match(grep("Thermoproteota", node_vector_bac, value = TRUE), node_vector_bac)
# 
# grep("Actinomycetota", node_vector_bac, value = TRUE)
# match(grep("Actinomycetota", node_vector_bac, value = TRUE), node_vector_bac)
# 
# grep("Desulfobacterota", node_vector_bac, value = TRUE)
# match(grep("Desulfobacterota", node_vector_bac, value = TRUE), node_vector_bac)
# match(grep("Desulfobacterota_B", node_vector_bac, value = TRUE), node_vector_bac)
# 
# grep("Bacteroidota", node_vector_bac, value = TRUE)
# match(grep("Bacteroidota", node_vector_bac, value = TRUE), node_vector_bac)
# 
# grep("Verrucomicrobiota", node_vector_bac, value = TRUE)
# match(grep("Verrucomicrobiota", node_vector_bac, value = TRUE), node_vector_bac)
# 
# grep("Chloroflexota", node_vector_bac, value = TRUE)
# match(grep("Chloroflexota", node_vector_bac, value = TRUE), node_vector_bac)
# 
# grep("Eremiobacterota", node_vector_bac, value = TRUE)
# match(grep("Eremiobacterota", node_vector_bac, value = TRUE), node_vector_bac)
# 
# grep("Patescibacteria", node_vector_bac, value = TRUE)
# match(grep("Patescibacteria", node_vector_bac, value = TRUE), node_vector_bac)
# 
# grep("Pseudomonadota", node_vector_bac, value = TRUE)
# match(grep("Pseudomonadota", node_vector_bac, value = TRUE), node_vector_bac)

# grep("Phycisphaerae", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Phycisphaerae", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)
# 
# grep("Acidobacteriota", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Acidobacteriota", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)
# 
# grep("Actinomycetota", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Actinomycetota", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)
# 
# grep("Myxococcota", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Myxococcota", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)
# 
# grep("Bacteroidota", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Bacteroidota", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)
# 
# grep("Verrucomicrobiota", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Verrucomicrobiota", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)
# 
# grep("Chloroflexota", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Chloroflexota", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)
# 
# grep("Eremiobacterota", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Eremiobacterota", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)
# 
# grep("Patescibacteria", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Patescibacteria", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)
# 
# grep("Patescibacteria", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Patescibacteria", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)

# grep("Gammaproteobacteria", node_vector_bac_TOOL_MAGS, value = TRUE)
# match(grep("Gammaproteobacteria", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)

grep("Gammaproteobacteria", node_vector_bac_TOOL_MAGS, value = TRUE)

## [1] "'1.0:c__Gammaproteobacteria'"

match(grep("Gammaproteobacteria", node_vector_bac_TOOL_MAGS, value = TRUE), node_vector_bac_TOOL_MAGS)

## [1] 259

Sankey Setup

NEON_MAGs_ind <- NEON_MAGs %>% 
  filter(`Assembly Type` == "Individual") 
NEON_MAGs_co <- NEON_MAGs %>% 
  filter(`Assembly Type` == "Combined") 

# Select the GTDB Taxonomic lineage and separate into taxonomic levels
sankey_data <- NEON_MAGs_co %>% 
  select(`GTDB-Tk Taxonomy Lineage`) %>% 
  # NAs are likely Archaea
  replace_na(list(`GTDB-Tk Taxonomy Lineage` = 'Archaea')) %>% 
  # Pavian format requires p__ etc
  separate(`GTDB-Tk Taxonomy Lineage`, c("Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"), "; ")

## Warning: Expected 7 pieces. Missing pieces filled with `NA` in 624 rows [1, 2, 3, 4, 5,
## 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, ...].

# Fill in the NAs with the taxonomic the higher taxonomic level to the left
sankey_data[] <- t(apply(sankey_data, 1, zoo::na.locf))

# Put the data into a format that can be read by the Sankey App

sankey_data <- sankey_data %>% 
  unite(col = "classification", c(Domain, Phylum, Class, Order, Family, Genus, Species), sep='; ') %>% 
  mutate_at("classification", str_replace, "Archaea", "d__Archaea") %>% 
  mutate_at("classification", str_replace, "Bacteria", "d__Bacteria") %>%  
  mutate_at("classification", str_replace, "; ", "|p__") %>% 
  mutate_at("classification", str_replace, "; ", "|c__") %>% 
  mutate_at("classification", str_replace, "; ", "|o__") %>% 
  mutate_at("classification", str_replace, "; ", "|f__") %>% 
  mutate_at("classification", str_replace, "; ", "|g__") %>% 
  mutate_at("classification", str_replace, "; ", "|s__")  

# Create format for Pavian with counts for each taxonomic level
sankey_data_s <- sankey_data
sankey_data_g <- sankey_data
sankey_data_f <- sankey_data
sankey_data_o <- sankey_data
sankey_data_c <- sankey_data
sankey_data_p <- sankey_data
sankey_data_d <- sankey_data

sankey_data_g$classification <- sub("\\|s__.*", "", sankey_data_g$classification)  
sankey_data_f$classification <- sub("\\|g__.*", "", sankey_data_f$classification)  
sankey_data_o$classification <- sub("\\|f__.*", "", sankey_data_o$classification)  
sankey_data_c$classification <- sub("\\|o__.*", "", sankey_data_c$classification)  
sankey_data_p$classification <- sub("\\|c__.*", "", sankey_data_p$classification)  
sankey_data_d$classification <- sub("\\|p__.*", "", sankey_data_d$classification)  

sankey_data_allTaxa <- bind_rows(sankey_data_s, sankey_data_g, sankey_data_f, sankey_data_o, sankey_data_c, sankey_data_p, sankey_data_d) %>% 
  mutate(classification = as.factor(classification)) %>% 
  count(classification) %>% 
# rename for Pavian format
  rename(`#SampleID` = `classification`) %>% 
  rename(`Metaphlan2_Analysis` = `n`) 

# Write file to input to Pavian Sankey
write_tsv(sankey_data_allTaxa, "data/NEON/NEON_MAG_co_pavian.txt")

Plot theme

# theme_classic(axis.text.x = element_text(color="grey20", size = 12,angle = 90, hjust = 0.5, vjust = 0.5), 
#                             axis.text.y = element_text(color = "grey20", size = 12), text=element_text(size = 16))

John_theme <-theme(axis.text.x=element_text(angle=45, vjust=1, hjust=1, color="black", face='italic'),axis.title.x=element_text(size = 15),
                   axis.text.y=element_text(color="black"),axis.title.y=element_text(size = 15))

Abstract:

Introduction:

    Carbon emissions from industrial activity has led to numerous changes to the global climate that threaten the ecosystems humanity depends on for industrial agriculture. Rising temperatures has caused the melting of glaciers and permafrost releasing bacterial species that have been dormant for millennium (source). Additionally, The higher green house gas atmospheric content has lead to the acidification of both ocean and ground water (source). The changing climate has also lead to species migration. With the recent passing of the 1.5 Celsius average global temperature milestone set by ORG, it is imperative that society adapt to our changing world.

    In the face of climate and antibiotic challenges, plants have developed symbiotic relationships with bacteria. PLANT BACTERIA BIOCONTROL EX. PLANT NITROGEN RELATION. Thus, it has been proposed that humanity’s crops could be better insulated to ecological changes by exploiting these relationships. While several beneficial bacterial species have identified, the vast majority of the bacterial kingdom remains sequenced. Additionally, with their ability to rapidly evolve in the face of ecological challenges, new species with more robust tolerances to climate change influences will only grow with time. Thus, soil bacterium represent a vast untapped resource of climate change resistant proteins, biocontrol agents, and nitrogen fixators. Data collection effort by organizations like the National Ecological Observatory Network, provide a valuable genomic resource for phylogenetic analyses to determine the identities potential beneficial bacteria as well as monitoring the population changes caused by a changing climate.

Figure 1:Phylogenetic Tree of all MAG

plottttttt <-ggtree(tree_bac_node_Gammaproteobacteria, layout="circular", branch.length="none")
n=1
while (n!=29) {
  if (is.na(phylumss[n,3])) {
    
  } else {
  plottttttt <-plottttttt + geom_cladelab(node=as.integer(phylumss[n,3]), label=as.character(phylumss[n,1]),size=10, align=TRUE, angle='auto', offset.text=1, textcolor=phylumss[n,4] ,barsize=1.5, fontsize=5, barcolor=as.character(phylumss[n,4]))+geom_hilight(node=as.integer(phylumss[n,3]), fill=as.character(phylumss[n,4], alpha=.6))
  }
  n=n+1
}
plottttttt

Figure 1: Phylogenetic Tree of all bacterial MAGs collected in GOLD Study ID Gs0161344 by the National Ecological Observatory Network with phylum labels.

Figure 2: Sankey plot of all NEON Individual assembly MAGs

knitr::include_url("data/lab14/sankey-NEON_MAG_ind_pavian.txt.html")

Figure 2: Sankey plot of all NEON Individual assembly MAGs.

 

    This study’s genomic data set was collected from soil samples by the National Ecological Observatory Network (NEON) from locations across the United States in GOLD Study ID Gs0161344. There were 1754 total MAGs with PERCENT been novel species of bacteria. To make analyses more feasible, this report will only comment on two data subsets, MAGs belonging to the class Gammaproteobacteria, and MAGs belonging found at Toolik Field Station, Alaska USA.

 

Figure 3:Uprooted maximum-likelyhood phylogentic tree of gammaproteobactria

Figure 3: Uprooted maximum-likelyhood phylogentic tree of gammaproteobactria based on 120 concatenated single copy proteins sequences from 780 reference genomes (Liao et al. 2020). Figure adapted from Figure 2 of Liao et al.

 

    The class Gammaproteobacteria, under the phylum Pseudomondata, is made up of around 381 genera that thrive in marine, terrestial, and eukaryotic host ecosystems (Liao et al. 2020). Historically, this class has be defined phylogenetically by 16s rRNA sequence homology (Williams and Kelly 2013). Some notable members of this class include Escherichia coli, Vibrio fischeri, and Pseudomonas aeruginosa. INSERT SOIL EXAMPLES. This class has great diversity of morphologies with rod, cocci, spirilla, and filaments all represented (Williams et al. 2010). Additionally, species in class display a variety of trophisms including chemoautotrophs and photoautotrophs (Gao, Mohan, and Gupta 2009).

 

Figure 4: Toolik Field Station, Alaska USA

Figure 4: Toolik Field Station, Alaska USA (University of Alaska Fairbanks n.d.)

 

    Located 400 miles north from Fairbanks, Alaska at the foot of the Brooks mountain range, biodiversity at Toolik Field Station is heavily influenced by its harsh winters where temperatures can reach -50⁰F. It is home to a variety of fauna including caribou, loons, voles, and polar bears. Located above the northern tree line, the vegetation in the tundra here mainly consists of birch, willow, sedges and grass. The site contains a large range of soil conditions, including layers of permafrost, created by glacial action (NEON 2023).

    This study examines the genomic content and environmental conditions of bacteria found at the Toolik Field station to help establish a reference population for future comparisons of bacterial population changes.

Methods:

Data Processing:

    Microbial samples analyzed in this study were collected from soil samples taken from NEON observation sites across the United States and sequenced via high throughput Illumina sequencing. Sequence results were then processed and annotated by the DOE JGI Metagenome Workflow for its inclusion in the Integrated Microbial Genomes and Microbiomes (IGM/M) Database and Joint Genomic Institute ’s Genomes Online Database (JGI GOLD). Briefly this workflow consists of the following steps: (1) Assembly of contigs and read alignment to assembled contigs. Contigs are additionally processed for quality control. (2) Feature prediction of coding and non-coding genes, as well as CRISPR sequences. (3) Functional annotation, in which predicted features are assigned identifiers based on sequence similarity. (4) Taxonomic annotation in which contig-level phylogenetic assignments are made based on functional annotations. (5) Binning by high- and medium-quality genome bins. Bins are additionally screened for contamination. A detailed explanation of the workflow can be found in Clum et al., ASM mSystems, 2021.

Figure Preparation:

    The figures of this study were formatted with the following packages in R: tidyverse,knitr, ggtree, TDbook #A Companion Package for the Book “Data Integration, Manipulation and Visualization of Phylogenetic Trees” by Guangchuang Yu (2022, ISBN:9781032233574). , ggimage, rphylopic, treeio, tidytree, ape, TreeTools, phytools, ggnewscale, ggtreeExtra, ggstar, DT (GGTREE SOURCES)

Results:

NEON Study 6 graphs

Figure 5: Phylogenetic tree with the Gammaproteobacteria class of Psedomondata highlighted in blue

ggtree(tree_bac, layout="circular", branch.length="none") +
    geom_hilight(node=as.integer(phylumss[1,3]), fill=as.character(phylumss[1,4], alpha=.6)) +
    geom_cladelab(node=as.integer(phylumss[1,3]), label=as.character(phylumss[1,1]),size=10, align=TRUE, angle='auto', offset.text=1, textcolor=phylumss[1,4] ,barsize=1.5, fontsize=5, barcolor=as.character(phylumss[1,4]))+
    geom_hilight(node=3048, fill="steelblue", alpha=.6) +
    geom_cladelab(node=3048, label="Gammaproteobacteria", align=TRUE, angle='auto', offset=1,  
                  offset.text=0.5 , textcolor='steelblue', barcolor='steelblue',barsize=1.5, fontsize=5)

Figure 5: Phylogenetic tree of all bacterial MAGs collected in GOLD Study ID Gs0161344 by the National Ecological Observatory Network with the Gammaproteobacteria class of Pseudomondata highlighted in blue.

Figure 6:

NEON_MAGs_bact_ind %>%
  ggplot(aes(x=fct_rev(fct_infreq(Phylum)), fill=`Site ID`))+geom_bar(position="dodge")+coord_flip()+labs(x="Phylum", y="NEON MAGs (n)")+theme_classic()+theme(axis.text.x=element_text(color="black"),axis.title.x=element_text(size = 15), axis.text.y=element_text(color="black",face = 'italic'),axis.title.y=element_text(size = 15), legend.title=element_text(size=15), legend.text=element_text(size=10))+ scale_y_continuous(limits=c(0,100),breaks = c(0,10,20,30,40,50,60,70,80,90,100))                                                                                                                                 

Figure 6: NEON MAG Distribution by Phylum. NEON site distribution of MAGs collected in GOLD Study ID Gs0161344 organized by phylum.

Figure 7:

NEON_MAGs_bact_ind_Novel %>% 
  ggplot(aes(x=fct_rev(fct_infreq(`Site ID`)), fill=`Site ID`))+geom_bar(show.legend=FALSE)+coord_flip()+labs(x="Site ID", y="Total Novel Bacteria (n)")+theme_classic()+theme(axis.text.x=element_text(color="black"),axis.title.x=element_text(size = 15), axis.text.y=element_text(color="black"))

Figure 7: Novel Bacteria MAG NEON Site Distribution. Novel Bacteria were determined from MAGs constructed from individual assemblies. Novel indicates the MAGs could not be placed in an existing group at the species, genus or family level.  

    The vast majority of bacteria found in this study were determined to be novel species with PERCENT being unable to place phylogenetically at the genus level.

  ### Figure 8:

NEON_MAGs_bact_ind %>% 
  filter(is.na(Class) | is.na(Order) | is.na(Family) | is.na(Genus) ) %>%
  ggplot(aes(x=fct_rev(`Phylum`), fill=`Phylum`))+geom_bar(show.legend=FALSE)+coord_flip()+labs(x="Phylum", y="Novel Genera (n)")+theme_classic()+theme(axis.text.x=element_text(color="black"),axis.title.x=element_text(size = 15), axis.text.y=element_text(color="black",face = 'italic'))+scale_y_continuous(limits = c(0,150), breaks = c(0,10,20,30,40,50,60,70,80,90,100,110,120,130,140,150))

Figure 8: Novel Bacteria Distribution by Phyla. Novel bacteria were determined from MAGs constructed from individual assemblies in GOLD Study ID Gs0161344. Novel indicates the MAGs could not be placed in an existing group at the species, genus or family level.

Figure 9:

NEON_MAGs_metagenomes_chemistry_Bacteria <-NEON_MAGs_metagenomes_chemistry %>%
  filter(Domain=="Bacteria") %>% 
  mutate(`Genome Size (Kbp)`=as.integer(`Total Number of Bases`/1000)) 

NEON_MAGs_metagenomes_chemistry_Bacteria %>%
  ggplot(aes(x=`Phylum`,y=`Genome Size (Kbp)`,color=`Phylum`))+geom_boxplot(show.legend = FALSE)+scale_y_continuous(limits=c(0,15000), breaks=c(0,2500,5000,7500,10000,12500,15000))+theme_classic()+labs(title="A", x="Phylum", y="Genome Size (Kbp)")+John_theme+theme(title=element_text(size=20))+
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Bacteria, aes(x=`Gene Count`, y=`Genome Size (Kbp)`, color=`Phylum`))+geom_point()+labs(title="B", x="Gene Count (n)", y="")+scale_y_continuous(limits=c(0,15000), breaks=c(0,2500,5000,7500,10000,12500,15000))+scale_x_continuous(limits=c(0,15000), breaks=c(0,2500,5000,7500,10000,12500,15000))+theme_classic()+theme_classic()+theme(axis.text.x=element_text(color="black"),axis.title.x=element_text(size = 15), axis.text.y=element_text(color="black"), legend.title=element_text(size=15),legend.text=element_text(size=10),title=element_text(size=20))

Figure 9: A) Boxplot of MAG genome size (kbp) for all bacterial phyla found in GOLD Study ID Gs0161344. B) Scatter plot of MAG Gene count vs genome size (kbp) for all bacterial MAGs in GOLD Study ID Gs0161344. MAGs are colored by phylum.

 

    Terrestrial bacteria are known to have large genomes encoding thousands genes. This is due in larger part to the diverse environment they are exposed to. Their larger genomes allow for the expression of multiple metabolic phenotypes that allow them to adapt to environmental challenges. NEON samples analyzed in this study had a broad spread of genome sizes with the minimum genome and maximum genomes sizes being 753 from the phylum Chloroflexota and 12,584 kbp from the phylum Actinomycetota, respectively (Fig. 9). There was a linear relationship between gene count and genome for all NEON samples, with a rough 1,000 bp per gene ratio (Fig. 9).

 

Gammaproteobacteria 8 graphs

Figure 10: Sankey plot of Individual Assemebly Gammmaproteobacteria MAGs.

knitr::include_url("data/lab14/sankey-NEON_MAG_ind_Gpro.txt.html")

Figure 10: Sankey plot of individual assembly Gammmaproteobacteria MAGs in GOLD Study ID Gs0161344.

Figure 11: Phylogenetic Tree of Gammaproteobacteria MAGs with total number of bases and ecosystem subtype markers labels.

ggtree(tree_Gammaproteobacteria, layout="circular")  %<+%
  NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria + 
  geom_point2(mapping=aes(color=`Ecosystem Subtype`, size=`Total Number of Bases`))+theme( legend.title=element_text(size=15),legend.text=element_text(size=10))

## Warning: Removed 123 rows containing missing values or values outside the scale range
## (`geom_point_g_gtree()`).

Figure 11: Phylogenetic Tree of Gammaproteobacteria with Ecosystem Subtype and Number of Bases markers. This tree includes MAG in GOLD Study ID Gs0161344 filtered to those annotated as belonging to the class Gammaproteobacteria.

Figure 12:

NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria %>%
  ggplot(aes(x=Family))+geom_bar(aes(fill=Family),position=position_dodge2(width=0.9, preserve="single"),show.legend=FALSE)+coord_flip()+facet_wrap(vars(Order), scales="free_y", ncol=4)+labs(x="Family", y="MAGs (n)")+theme_classic()+theme(axis.text.x=element_text(color="black"),axis.title.x=element_text(size = 15), axis.text.y=element_text(color="black",face = 'italic'), legend.title=element_text(size=15),legend.text=element_text(size=10),strip.text = element_text(size=15, face = "italic"))+scale_y_continuous(limits=c(0,75), breaks=c(0,15,30,45,60))

Figure 12: Distribution of Gammaproteobacteria MAGs by Order. This includes MAG reads from all NEON sites in GOLD Study ID Gs0161344 filtered to those annotated as belonging to the class Gammaproteobacteria.

Figure 13:

NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria %>%
  mutate(`Genome Size (Kbp)`=as.integer(`Total Number of Bases`/1000)) %>%
  ggplot(aes(x=`Order`,y=`Genome Size (Kbp)`,color=`Order`))+geom_boxplot(show.legend = FALSE)+scale_y_continuous(limits=c(0,15000), breaks=c(2500,5000,7500,10000,12500,15000))+theme_classic()+labs(x="Order", y="Genome Size (Kbp)")+John_theme

Figure 13: Distribution of Genome Size (kbp) for Gammaproteobacteria Members. Boxplots includes MAG reads from all NEON sites filtered to those annotated as belonging to the class Gammaproteobacteria  

    NEON MAGs assigned to the Gammaproteobacteria class were found in all ecosystem subtypes (Fig. 10). Unlike the larger NEON data set, the distribution of genome size of Gammaproteobacteria members was fairly narrow with members averaging between 2000 and 5000 kbp (Fig. 12). With the exception of Burkholderiales,Steroidobacterales, and Xanthomonadales, this was largely due to the fewer MAGs in each order(Fig.10). The vast majority of Gammaproteobacteria annotated in this study were novel species with only two bacteria belonging to the Xanthomonadales order assigned as Stenotrophomonas stenotrophomonas sp024519465. Steroidobacterales had by far the most annontated members, while Burkholderiales had the most family member groups (Fig. 11).
 

Figure 14:

NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria %>%
     ggplot(aes(y=`soilTemp`,x=`Family`, color=`Order`), size=1)+geom_point(show.legend=FALSE)+scale_y_continuous(limits=c(0,50)) +labs(title="A", y="Soil Temperature", x="")+theme_classic()+John_theme+theme(title=element_text(size=20))+
  
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria,aes(y=`soilInWaterpH`,x=`Family`, color=`Order`))+geom_point()+scale_y_continuous(limits=c(0,14),breaks =rep(0:14) )+labs(title="B", y="pH", x="")+theme_classic()+theme(title=element_text(size=20),legend.text = element_text(size=10,face = 'italic'),legend.title = element_text(size=15))+John_theme+
  
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria,aes(y=`nlcdClass`,x=`Family`, color=`Order`))+geom_point(show.legend=FALSE)+labs(title="C", y="Vegetation Class", x="Family")+theme_classic()+John_theme+theme(title=element_text(size=20))+
  
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria,aes(y=`Ecosystem Subtype`,x=`Family`, color=`Order`,))+geom_point()+labs(title="D", y="Ecosystem Subtype", x="Family")+theme_classic()+theme(title=element_text(size=20), legend.title=element_text(size=15), legend.text=element_text(size=10))+John_theme

## Warning: Removed 39 rows containing missing values or values outside the scale range
## (`geom_point()`).
## Removed 39 rows containing missing values or values outside the scale range
## (`geom_point()`).

Figure 14: Ecological Conditions of Gammaproteobacteria Samples. A) Scatterplot of sample soil temperature vs Gammaproteobacteria families found in GOLD Study ID Gs0161344. Points are colored by order group. B) Scatterplot of sample soil pH in water vs Gammaproteobacteria families found in GOLD Study ID Gs0161344. Points are colored by order group. C) Scatterplot of sample National Land Cover Database Vegetation Type vs Gammaproteobacteria families found in GOLD Study ID Gs0161344. Points are colored by order group. D) Scatterplot of sample ecosystem subtype vs Gammaproteobacteria families found in GOLD Study ID Gs0161344. Points are colored by order group.  

    Members of Gammaproteobacteria were found in a variety of ecosystem conditions. The soil pH of all Gammaproteobacteria samples was largely neutral to mildly acidic with lowest pH around 4 (Fig. 4). Overall, the vegetation class of sedge and grassland herbaceous and contained the least amount of family groups in Gammproteobacteria (Fig. 13). This is not too surprising for sedge herbaceous as this vegetation class is only found in one Alaskan NEON site (Sup. Fig. 1). However, grassland herbaceous vegetation is present in 5 out of the 13 sample sites (Sup. Fig 2). Interestingly, despite being the Gammaproteobacteria order with the most MAGs and existing in a variety of vegetation classes, soil pH and temperatures, no members of the Steroidobacterales order were found in tropical forest or desert ecosystems sampled in this study(Fig. 13). These ecosystem subtypes correspond to NEON sites in Puerto Rico and Arizona, USA, respectively (Sup.Fig 2).

 

Figure 15:Steroidobacterale Steroidobacteraceae

NEON_MAGs_metagenomes_chemistry_Steroidobacterales <-NEON_MAGs_metagenomes_chemistry_Steroidobacterales  %>%
  mutate(`Genome Size (Kbp)`=as.integer(`Total Number of Bases`/1000))
#Ecosubtype
NEON_MAGs_metagenomes_chemistry_Steroidobacterales  %>%
  ggplot(aes(x=Genus, y=`Ecosystem Subtype`,color=Genus))+geom_point(show.legend=FALSE)+labs(title="A", x="", y="Ecosystem Subtype")+theme_classic()+John_theme+theme(title=element_text(size=20))+
#siteID  
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Steroidobacterales,aes(x=Genus, `Site ID.x`,color=Genus))+geom_point(show.legend=FALSE)+labs(title="B", x="", y="Site ID")+theme_classic()+John_theme+theme(title=element_text(size=20))+
#genomesize  
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Steroidobacterales, aes(x=`Genus`,y=`Genome Size (Kbp)`,color=Genus))+geom_boxplot(show.legend = FALSE)+scale_y_continuous(limits=c(0,15000), breaks=c(2500,5000,7500,10000,12500,15000))+theme_classic()+labs(title="C", x="Genus", y="Genome Size (Kbp)")+John_theme+theme(title=element_text(size=20))+
#genus count
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Steroidobacterales,aes(x=Genus,fill=Genus))+geom_bar(show.legend=FALSE)+labs(title="D", x="Genus", y="MAGs (n)")+theme_classic()+scale_y_continuous(limits=c(0,50), breaks=c(0,10,20,30,40,50))+John_theme+theme(title=element_text(size=20))

Figure 15: A) Dotplot of ecosystem subtype each genus of Steroidobacteraceae was found in. B) Dotplot of the NEON sites each genus of Steroidobacteraceae was found in. C) Boxplot of MAG genome sizes in Kbp for each genus of Steroidobacteraceae. D) Total MAG counts of each genus of Steroidobacteraceae. All samples belong to the GOLD Study ID Gs0161344.

Figure 16: Steroidobacteraceae BOG-1198

NEON_MAGs_metagenomes_chemistry_Bog <-NEON_MAGs_metagenomes_chemistry_Steroidobacterales  %>%
  filter(str_detect(Genus,"Bog-1198"))

NEON_MAGs_metagenomes_chemistry_Bog %>%         
         ggplot(aes(x=`Ecosystem Subtype`))+geom_bar(show.legend=FALSE,fill='black')+labs(title="A", x="Ecosystem Subtype", y=" MAGs (n)")+theme_classic()+theme(axis.text.x=element_text(angle=45, vjust=1, hjust=1, color="black"),axis.title.x=element_text(size = 15),
                   axis.text.y=element_text(color="black"),axis.title.y=element_text(size = 15), title=element_text(size=20))+scale_y_continuous(limits=c(0,10), breaks=c(0,1,2,3,4,5,6,7,8,9,10))+
  
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Bog, aes(x=`Site ID.x`))+geom_bar(show.legend=FALSE,fill='black')+labs(title="B", x="Site ID", y=" MAGs (n)")+theme_classic()+theme(axis.text.x=element_text(color="black"),axis.title.x=element_text(size = 15),
                   axis.text.y=element_text(color="black"),axis.title.y=element_text(size = 15), title=element_text(size=20))+scale_y_continuous(limits=c(0,10), breaks=c(0,1,2,3,4,5,6,7,8,9,10))

## Warning: Removed 1 row containing missing values or values outside the scale range
## (`geom_bar()`).
## Removed 1 row containing missing values or values outside the scale range
## (`geom_bar()`).

Figure 16: Steroidobacteraceae BOG-1198 Ecosystem subtype and site distribution. A) Barchart of BOG-1198 MAGs found in each ecosystem subtype. B) Barchart of BOG-1198 MAGs found at each Site. All samples belong to the GOLD Study ID Gs0161344.

 

    Members in the order Steriobacterales were further examined to see if their high population is correlated with genome size or sample location. Only the Steroidobacteraceae family was found under the order. This family contain 7 genera with the genus BOG-1198 accounting for 30 of the 50 of Steriobacterales MAGs (figs. 10,14). Once again the distribution of genome size appears correlated to the total MAG counts for each genera in the Steroidobacteraceae family, with the higher populations corresponding to larger deviation in genome size. Given that BOG-1198 accounted for a majority of Steriobacterales MAGs, the genus was further examined. Members of this genus were found in several ecosystem subtypes and sample sites located in the northern United States. The majority Individual Assemblies of Steroidobacteraceae BOG-1198 MAGs were found at one of the three Alaskan sample sites (Figure 16).Note that all combined assembly MAGs were given the shrubland ecosystem subtype. A third of all BOG-1198 MAGs were coassembled.

 

Figure 17: Burkholderiales

NEON_MAGs_metagenomes_chemistry_Burkholderiales <-NEON_MAGs_metagenomes_chemistry_Burkholderiales  %>%
  mutate(`Genome Size (Kbp)`=as.integer(`Total Number of Bases`/1000))

NEON_MAGs_metagenomes_chemistry_Burkholderiales  %>%
  ggplot(aes(x=Genus, y=`Ecosystem Subtype`,color=`Family`))+geom_point(show.legend=FALSE)+labs(title="A", x="", y="Ecosystem Subtype")+theme_classic()+John_theme+theme(title=element_text(size=20))+
  
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Burkholderiales,aes(x=Genus,y= `Site ID.x`,color=`Family`))+geom_point()+labs(title="B", x="", y="Site ID")+theme_classic()+John_theme+theme(title=element_text(size=20), legend.text = element_text(size=10, face='italic'),legend.title = element_text(size=15))+
  
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Burkholderiales, aes(x=`Genus`,y=`Genome Size (Kbp)`,color=`Family`))+geom_boxplot(show.legend = FALSE)+scale_y_continuous(limits=c(0,15000), breaks=c(2500,5000,7500,10000,12500,15000))+theme_classic()+labs(title="C", x="Genus", y="Genome Size (Kbp)")+John_theme+theme(title=element_text(size=20))+
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Burkholderiales,aes(x=Genus,fill=`Family`))+geom_bar()+labs(title="D", x="Genus", y="MAGs (n)")+theme_classic()+John_theme+theme(title=element_text(size=20),legend.text = element_text(size=10, face='italic'),legend.title = element_text(size=15))

Figure 17: Burkholderiales

Figure 18: Burkholderiales Burkholderiaceae

NEON_MAGs_metagenomes_chemistry_Burkholderiaceae <- NEON_MAGs_metagenomes_chemistry_Burkholderiales  %>%
   filter(str_detect(Family,"Burkholderiaceae" ))

  
ggplot(data=NEON_MAGs_metagenomes_chemistry_Burkholderiaceae, aes(x=`Ecosystem Subtype`,fill=Genus))+geom_bar(show.legend=FALSE)+labs(title="A", x="Ecosystem Subtype", y="MAGs (n)")+theme_classic()+theme(axis.title=element_text(size = 15),title=element_text(size=20), axis.text.y=element_text(color="black"), axis.text.x=element_text(angle=45, vjust=1, hjust=1, color="black"))+
  
  ggplot(data=NEON_MAGs_metagenomes_chemistry_Burkholderiaceae, aes(x=`Site ID.x`, fill=Genus))+geom_bar()+labs(title="B", x="Site ID", y="MAGs (n)")+theme_classic()+theme(axis.title=element_text(size = 15),axis.text.y=element_text(color="black"), axis.text.x=element_text(color="black", angle=45, vjust=1, hjust=1), title=element_text(size=20),legend.text = element_text(size=10, face='italic'),legend.title = element_text(size=15))

Figure 18: Burkholderiales Burkholderiaceae

 

    Members of the order Burkholderiales were also examined further at the genus level to determine if their broader diversity corresponded to the variety of ecosystems they were found in. Indeed, members of this order were found across the United States in several different ecosystem subtypes. Individually assembled members of the Burkholderiaceae including the genera Caballeronia, Herbaspirillum, and Paraburkholderi, were found mainly temperate forests with some members also found in tundra and and Boreal forest/Taiga subtypes (Fig. 16, 17). Interestingly, genera genome size distribution appears not to be correlated to the amount genera members. Despite only having 4 MAGs from the Niwot Ridge site in Colorado the Herbaspirillum genera contained a broad range of genome sizes. The Caballeronia genera, containing 5 MAGs, had a much tighter distribution of genome size (Fig. 16). Also of note is the appearance of the Trinicki genera in the Wind River Experimental Forest in Washington (Fig. 16,17). Trinicki members have prevously been found to form endosymbotic relations with the phyopathgenic fungi Rhizopus microsporus (Source).

 

Toolik 0/20 graphs

Figure 19: Sankey plot of Mags from Toolik Field Station

knitr::include_url("data/lab14/sankey-NEON_MAG_Toolik.txt.html")

Figure 19: Sankey plot of Mags from Toolik Field Station

Figure 20: Phylogenetic tree of all MAGs collected at Toolik in GOLD Study ID Gs0161344

ggtree(tree_bac_TOOL_MAGs, layout="circular", branch.length="none") +
    geom_hilight(node=258, fill="grey", alpha=.6) +
    geom_cladelab(node=258, label="Pseudomonadota", align=TRUE, angle='auto', 
                  offset.text=0.5 , textcolor='black', barcolor='grey',barsize=1.5, fontsize=5)+
    geom_hilight(node=259, fill="steelblue", alpha=.6) +
    geom_cladelab(node=259, label="Gammaproteobacteria", align=TRUE, angle='auto', offset=0.75,  
                  offset.text=0.5 , textcolor='black', barcolor='steelblue',barsize=1.5, fontsize=5)

Figure 20: Phylogenetic tree of all MAGs collected in GOLD Study ID Gs0161344 by the National Ecological Observatory Network at Toolik Field Station, Alaska USA Gammaproteobacteria class of Psedomondata highlighted in blue.

Figure 21 TOOLIK distribution by Phylum

NEON_MAGs_metagenomes_chemistry_TOOL %>% 
  ggplot(aes(x=fct_rev(fct_infreq(Phylum)), fill=Order))+geom_bar()+coord_flip()+labs(x="Phylum", y="MAG Count (n)",fill="Order")+theme_classic()+theme(axis.title=element_text(size = 15),axis.text.y=element_text(color="black",face='italic'), axis.text.x=element_text(color="black"),legend.text = element_text(size=10, face='italic'),legend.title = element_text(size=15))

Figure 21: MAG Count by Phylum at Toolik Field Station.

Figure 21: NEON Site Sample Temperatures and pH

NEON_MAGs_metagenomes_chemistry %>%
     ggplot(aes(y=`soilTemp`,x=`Site ID.x`, color=`Site ID.x`), size=1)+geom_point(show.legend = FALSE)+scale_y_continuous(limits=c(0,50),breaks = c(10,20,30,40,50)) +labs(title="A", y="Soil Temperature", x="Site ID")+theme_classic()+theme(title=element_text(size=15),axis.title=element_text(size = 15),axis.text.y=element_text(color="black"), axis.text.x=element_text(color="black", angle=45, vjust=1, hjust=1))+
     ggplot(data=NEON_MAGs_metagenomes_chemistry,aes(y=`soilInWaterpH`,x=`Site ID.x`, color=`Site ID.x`), size=1)+geom_point(show.legend = FALSE)+scale_y_continuous(limits=c(0,14),breaks=c(1:14)) +labs(title="B", y="Soil pH", x="Site ID")+theme_classic()+theme(title=element_text(size=15),axis.title=element_text(size = 15),axis.text.y=element_text(color="black"), axis.text.x=element_text(color="black", angle=45, vjust=1, hjust=1))

## Warning: Removed 625 rows containing missing values or values outside the scale range
## (`geom_point()`).

## Warning: Removed 624 rows containing missing values or values outside the scale range
## (`geom_point()`).

Figure 21: NEON Site Sample Temperatures and pH. A) Scatterplot of sample soil temperatures at each NEON site. B) Scatterplot of sample soil pHs in water at each NEON site.

Figure 22:

NEON_MAGs_metagenomes_chemistry_Alaska %>%
     ggplot(aes(x=`Phylum`,y=`soilTemp`, color=`Phylum`), size=1)+geom_point(show.legend=FALSE)+facet_wrap(vars(Site.x), scales="free_y", ncol=3)+scale_y_continuous(limits=c(0,10)) +labs(y="Soil Temperature", x="Phylum")+theme_classic()+John_theme+theme(strip.text = element_text(size=13))

## Warning: Removed 20 rows containing missing values or values outside the scale range
## (`geom_point()`).

Figure 22: Soil temperatures

Figure 23:

NEON_MAGs_metagenomes_chemistry_Alaska %>%
     ggplot(aes(x=`Phylum`,y=`soilInWaterpH`, color=`Phylum`), size=1)+geom_point(show.legend = FALSE)+facet_wrap(vars(Site.x), scales="free_y", ncol=3)+scale_y_continuous(limits=c(0,14),breaks =rep(0:14)) +labs(y="Soil pH", x="Phylum")+theme_classic()+John_theme+theme(strip.text = element_text(size=13))

Figure 23: Sample soil pH in water

Figure 24:

NEON_MAGs_metagenomes_chemistry_Alaska %>%
     ggplot(aes(x=`Phylum`,y=`nlcdClass`, color=`Phylum`), size=1)+geom_point(show.legend = FALSE)+facet_wrap(vars(Site.x), scales="free_y", ncol=3)+labs(y="Vegetation Class", x="Phylum")+theme_classic()+John_theme+theme(strip.text = element_text(size=10))

Figure 24: Sample National Land Class Vegetation Class

Figure 25:

NEON_MAGs_metagenomes_chemistry_Alaska %>%
     ggplot(aes(x=`Phylum`, fill=`Order`))+geom_bar()+facet_wrap(vars(Site.x), scales="free_y", ncol=3) +labs(y="MAGs (n)", x="Phylum")+theme_classic()+John_theme+theme(strip.text = element_text(size=10), legend.title=element_text(size=15), legend.text=element_text(size=10, face='italic'))

Figure 25: MAGs found at each Alaskan NEON Site.

Figure 26: TOOLIK distribution by Phylum

NEON_MAGs_metagenomes_chemistry_TOOL %>% 
  ggplot(aes(x=fct_rev(fct_infreq(Phylum)), fill=Order))+geom_bar()+coord_flip()+labs(x="Site", y="MAG Count (n)",fill="Order")+theme_classic()+theme(axis.text.x=element_text(color="black"),axis.title=element_text(size = 15), axis.text.y=element_text(color="black",face='italic'), legend.title=element_text(size=15),legend.text=element_text(size=10))+scale_y_continuous(limits=c(0,50),breaks = c(0,10,20,30,40,50))

Figure 26: MAG Count by Phylum at Toolik Field Station

Figure 27:

NEON_MAGs_metagenomes_chemistry_TOOL %>%
  mutate(`Genome Size (Kbp)`=as.integer(`Total Number of Bases`/1000)) %>%
  ggplot(aes(x=`Phylum`,y=`Genome Size (Kbp)`,color=`Phylum`))+geom_boxplot(show.legend = FALSE)+scale_y_continuous(limits=c(0,15000), breaks=c(2500,5000,7500,10000,12500,15000))+theme_classic()+labs(x="Phylum", y="Genome Size (Kbp)")+John_theme

Figure 27: Genome Size Distributions at Toolik Field Station

Figure 28:

ggtree(tree_bac_TOOL_MAGs)  %<+%
  NEON_MAGs_metagenomes_chemistry + 
  geom_tippoint(aes(colour=`Phylum`)) + 

# For unknown reasons the following does not like blank spaces in the names
  geom_facet(panel = "Gene Count (n)", data = NEON_MAGs_metagenomes_chemistry_TOOL_noblank, geom = geom_point, 
      mapping=aes(x = GeneCount, color=Phyla))+
  geom_facet(panel = "% GC Content ", data = NEON_MAGs_metagenomes_chemistry_TOOL_noblank, geom = geom_col, 
                aes(x = GCassembled,fill=Phyla), orientation = 'y', width = .6, show.legend=FALSE) +
  theme_tree2(legend.position=c(.1, .7),strip.text=element_text(size=15),axis.text=element_text(color = 'black'))

Figure 28: Genome content of bacteria found at Toolik Field Station. Left Panel: Phylogenetic tree of all MAGs found at Toolik Field Station, Alaska USA with markers for MAG phylum. Middle Panel: Gene Count of all Mags found at Toolik Field Station, Alaska USA. Points colored by MAG phylum. Right Panel: % GC Content of all MAGs found at Toolik Field Station, Alaska USA. Bar colored by MAG phylum.

Figure 29: Steroidobacterales

NEON_MAGs_metagenomes_chemistry_TOOL_Steroidobacterales %>%
ggplot( aes(x=`Genus`,y=`Genome Size (Kbp)`,color=Genus))+geom_boxplot(show.legend = FALSE)+scale_y_continuous(limits=c(0,15000), breaks=c(2500,5000,7500,10000,12500,15000))+theme_classic()+labs(title="A", x="Genus", y="Genome Size (Kbp)")+John_theme+theme(title = element_text(size=15))+
#genus count
  ggplot(data=NEON_MAGs_metagenomes_chemistry_TOOL_Steroidobacterales,aes(x=Genus,fill=Genus))+geom_bar(show.legend=FALSE)+labs(title="B", x="Genus", y="MAGs (n)")+theme_classic()+John_theme+theme(title = element_text(size=15))

Figure 29: Steroidobacterales A) Boxplot of sample genome size (kbp) in the Steroidobacterales family at Toolik Field Station, Alaska USA. B) Barplot of MAGs for each genus in the Steroidobacterales family found at Toolik Field Station, Alaska USA.

Figure 30: Burkholderiales

NEON_MAGs_metagenomes_chemistry_TOOL_Burkholderiales  %>%
  ggplot(aes(x=Genus,fill=`Family`))+geom_bar()+labs(x="Genus", y="MAGs (n)")+theme_classic()+John_theme+theme(legend.title = element_text(size=15),legend.text = element_text(size=10, face='italic'))+scale_y_continuous(limits=c(0,5),breaks=rep(0:5))

Figure 30: Genus distribution of Burkholderiales is wide spread at Toolik Field Station, Alaska USA. Barplot of MAGs in Burkholderiales Genera at Toolik Field Station, Alaska USA. NA represent novel genera in Burkholderiales

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Discussion:

Gammaproteobacteria

    Several notable genera in Burkholderiales were found in this study, Caballeronia, paraburkholderia (known nitrogen fixators and endosymbotes), trinickia Novel associated with phytopathogen from journal club

Toolik

Code

Lab 8

Lab 9

Lab 10

Lab 12

Lab 14

Lab 15

Lab 16

Gammaproteobacteria

Toolik

Supplemental Figures:

Supplemental Figure 1: NEON Site vs Vegetation subclass

NEON_MAGs_metagenomes_chemistry %>%
  ggplot(aes(y=`Site.x`, x=nlcdClass))+geom_point()+labs(title="NEON Site Vegetation Classes", y="Site", x="Vegetation Class")+theme_classic()+theme(axis.text.x=element_text(angle=45, vjust=1, hjust=1))

Supplemental Figure 2: NEON Site vs Ecosystem subclass

NEON_MAGs_metagenomes_chemistry %>%
  ggplot(aes(y=`Site.x`, x=`Ecosystem Subtype`))+geom_point()+labs(title="NEON Site Ecosystem Subtypes", y="Site", x="Ecosystem Subtype")+theme_classic()+theme(axis.text.x=element_text(angle=45, vjust=1, hjust=1))

### Figure 2: Sankey plot of all NEON Combined assembly MAGs

knitr::include_url("data/lab14/sankey-NEON_MAG_co_pavian.txt.html")

Figure 2: Sankey plot of all NEON combined assembly MAGs

Figure 2: Sankey plot of all NEON combined assembly Gammmaproteobacteria MAGs

knitr::include_url("data/lab14/sankey-NEON_MAG_co_Gpro.txt.html")

Figure 2: Sankey plot of all NEON combined assembly Gammmaproteobacteria MAGs

Figure 5:hylogenetic tree of all MAGs belonging to the class Gammaproteobacteria with Site location

ggtree(tree_Gammaproteobacteria)  %<+%
  NEON_MAGs_metagenomes_chemistry_Gammaproteobacteria + 
  geom_tippoint(aes(color=`Order`)) + 

# For unknown reasons the following does not like blank spaces in the names
  geom_facet(panel = "Gene Count", data = NEON_MAGs_metagenomes_chemistry_Gamma_noblank, geom = geom_point, 
      mapping=aes(x = GeneCount, color=Orders))+
  geom_facet(panel = "% GC Content ", data = NEON_MAGs_metagenomes_chemistry_Gamma_noblank, geom = geom_col, 
                aes(x = GCassembled,fill=Orders), orientation = 'y', width = .6, show.legend=FALSE) +
  theme_tree2(legend.position=c(.1, .7))

ggtree(tree_Gammaproteobacteria)  %<+%
  NEON_MAGs_metagenomes_chemistry + 
 xlim(0,20)+
  geom_point(mapping=aes(color=`Site.x`))

Figure 5: Phylogenetic tree of all MAGs belonging to the class Gammaproteobacteria with Gene count and %GC Content.

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

redo this because points are overlapping

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

Figure 1:

References:

GGtree Yu G (2022). Data Integration, Manipulation and Visualization of Phylogenetic Treess, 1st edition edition. Chapman and Hall/CRC. doi:10.1201/9781003279242, https://www.amazon.com/Integration-Manipulation-Visualization-Phylogenetic-Computational-ebook/dp/B0B5NLZR1Z/.

Xu S, Li L, Luo X, Chen M, Tang W, Zhan L, Dai Z, Tommy T. Lam, Guan Y, Yu G (2022). “Ggtree: A serialized data object for visualization of a phylogenetic tree and annotation data.” iMeta, 1(4), e56. doi:10.1002/imt2.56, https://onlinelibrary.wiley.com/doi/full/10.1002/imt2.56.

Yu G (2020). “Using ggtree to Visualize Data on Tree-Like Structures.” Current Protocols in Bioinformatics, 69(1), e96. doi:10.1002/cpbi.96, https://currentprotocols.onlinelibrary.wiley.com/doi/abs/10.1002/cpbi.96.

Yu G, Lam TT, Zhu H, Guan Y (2018). “Two methods for mapping and visualizing associated data on phylogeny using ggtree.” Molecular Biology and Evolution, 35, 3041-3043. doi:10.1093/molbev/msy194, https://academic.oup.com/mbe/article/35/12/3041/5142656.

Yu G, Smith D, Zhu H, Guan Y, Lam TT (2017). “ggtree: an R package for visualization and annotation of phylogenetic trees with their covariates and other associated data.” Methods in Ecology and Evolution, 8, 28-36. doi:10.1111/2041-210X.12628, http://onlinelibrary.wiley.com/doi/10.1111/2041-210X.12628/abstract.

gold Please cite: Supratim Mukherjee, Dimitri Stamatis, Cindy Tianqing Li, Galina Ovchinnikova, Jon Bertsch, Jagadish Chandrabose Sundaramurthi, Mahathi Kandimalla, Paul A. Nicolopoulos, Alessandro Favognano, I-Min A. Chen , Nikos C. Kyrpides and T.B.K. Reddy. Twenty-five years of Genomes OnLine Database (GOLD): data updates and new features in v.9. Nucl. Acids Res. (2022) doi: doi.org/10.1093/nar/gkac974

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8269246/

Gao, Beile, Ritu Mohan, and Radhey S. Gupta. 2009. “Phylogenomics and Protein Signatures Elucidating the Evolutionary Relationships Among the Gammaproteobacteria.” International Journal of Systematic and Evolutionary Microbiology 59 (2): 234–47. https://doi.org/10.1099/ijs.0.002741-0.

Liao, Hu, Xiaolan Lin, Yuqian Li, Mingming Qu, and Yun Tian. 2020. “Reclassification of the Taxonomic Framework of Orders Cellvibrionales, Oceanospirillales, Pseudomonadales, and Alteromonadales in Class Gammaproteobacteria Through Phylogenomic Tree Analysis.” mSystems 5 (5): 10.1128/msystems.00543–20. https://doi.org/10.1128/msystems.00543-20.

NEON, Collection. 2023. “Collection - Getting to Know the NEON Domains.” ArcGIS StoryMaps. https://storymaps.arcgis.com/collections/5765fc95c3c24297a5b9dc2c99e69e5c.

University of Alaska Fairbanks, Collection. n.d. “Photo Gallery Toolik Field Station.” Accessed April 2, 2024. https://www.uaf.edu/toolik/about/toolik-gallery.php.

Williams, Kelly P., Joseph J. Gillespie, Bruno W. S. Sobral, Eric K. Nordberg, Eric E. Snyder, Joshua M. Shallom, and Allan W. Dickerman. 2010. “Phylogeny of Gammaproteobacteria.” Journal of Bacteriology 192 (9): 2305–14. https://doi.org/10.1128/JB.01480-09.

Williams, Kelly P., and Donovan P. Kelly. 2013. “Proposal for a New Class Within the Phylum Proteobacteria, Acidithiobacillia Classis Nov., with the Type Order Acidithiobacillales, and Emended Description of the Class Gammaproteobacteria.” International Journal of Systematic and Evolutionary Microbiology 63 (Pt_8): 2901–6. https://doi.org/10.1099/ijs.0.049270-0.